Benchmarking to infer configuration of similar devices

1. A method for categorizing mobile devices, the method comprising:

distributing, by a server system, benchmark applications to a plurality of client mobile devices, the benchmark applications configured to at least one of produce or collect one or more dynamic and static parameters as performance metrics for each client mobile device;

receiving, by the server system, the performance metrics of the plurality of client mobile devices;

comparing, by the server system, the performance metrics of a client mobile device having an unknown mobile device type to the performance metrics of client mobile devices having known mobile device types;

categorizing, by the server system, the client mobile device having the unknown mobile device type with one or more client mobile devices having known mobile device types according to similarity of the performance metrics of the client mobile device having the unknown mobile device type to the performance metrics of the one or more of the client mobile devices having known mobile device types, wherein at least one of a central processing unit or graphics processing unit of the client mobile device having the unknown mobile device type is different than for the one or more of the client mobile devices having the known mobile device types;

identifying, by the server system, feature levels for at least one feature of a social media application on the categorized client mobile device having the unknown mobile device type; and

distributing, by the server system, the identified feature levels for the at least one feature of the social media application to the categorized client mobile device having the unknown mobile device type for use by the categorized client mobile device to configure at least one feature of the social media application on the categorized client mobile device having the unknown mobile device type in accordance with the identified feature levels for the at least one feature of the social media application on the categorized client mobile device having the unknown mobile device type for more efficient processing of the social media application at the identified feature levels on the categorized client mobile device having the unknown mobile device type.

2. The method of claim 1 , wherein the comparing comprises:

generating a signature from the performance metrics of the client mobile device having the unknown mobile device type; and

comparing the signature to signatures of client mobile devices having known mobile device types;

wherein the categorizing categorizes the client mobile device having the unknown mobile device type responsive to comparing the signatures.

3. The method of claim 2 , wherein the signature is a multi-dimensional signature and the comparing identifies a closest match in a multi-dimensional space.

4. The method of claim 2 , wherein the comparing the signature to the signatures comprises applying a fuzzy matching algorithm.

5. The method of claim 1 , wherein the categorizing comprises:

assigning the client mobile device having the unknown mobile device type into one of a plurality of categories, each category associated with one or more features and each feature having a feature level selected from a plurality of feature levels.

6. The method of claim 1 , wherein each of the benchmark applications has a specified time for completion.

7. The method of claim 6 , wherein one of the benchmark applications is selected from a group comprising determining how many primes are calculated within a first predetermined period of time and determining how many images are compared from an image set within a second predetermined period of time.

8. The method of claim 1 , wherein the method further comprises:

identifying that the client mobile device of the unknown mobile device type has one or more missing performance metrics;

requesting that the client mobile device of the unknown mobile device type perform the benchmark applications corresponding the one or more missing performance metrics; and

receiving the one or more missing performance metrics.

9. A system for categorizing mobile devices, the system comprising:

a memory that stores instructions; and

a processor configured by the instructions to perform operations comprising:

distributing benchmark applications to a plurality of client mobile devices, the benchmark applications configured to at least one of produce or collect one or more dynamic and static parameters as performance metrics for each client mobile device;

receiving the performance metrics from the plurality of client mobile devices;

detecting a client mobile device having an unknown mobile device type;

comparing the performance metrics of the client mobile device having the unknown mobile device type to the performance metrics of client mobile devices having known mobile device types;

categorizing the client mobile device having the unknown mobile device type with one or more client mobile devices having known mobile device types according to similarity of the performance metrics of the client mobile device having the unknown mobile device type to the performance metrics of the one or more of the client mobile devices having known mobile device types, wherein at least one of a central processing unit or graphics processing unit of the client mobile device having the unknown mobile device type is different than for the one or more of the client mobile devices having the known mobile device types;

identifying feature levels for at least one feature of a social media application on the categorized client mobile device having the unknown mobile device type; and

distributing the identified feature levels for the at least one feature of the social media application to the categorized client mobile device having the unknown mobile device type for use by the categorized client mobile device to configure at least one feature of the social media application on the categorized client mobile device having the unknown mobile device type in accordance with the identified feature levels for the at least one feature of the social media application on the categorized client mobile device having the unknown mobile device type for more efficient processing of the social media application at the identified feature levels on the categorized client mobile device having the unknown mobile device type.

10. The system of claim 9 , wherein the comparing comprises:

generating a signature from the performance metrics of the client mobile device having the unknown mobile device type; and

comparing the signature to signatures of client mobile devices having known mobile device types;

wherein the categorizing categorizes the client mobile device having the unknown mobile device type responsive to comparing the signatures.

11. The system of claim 10 , wherein the signature is a multi-dimensional signature and the comparing identifies a closest match in a multi-dimensional space.

12. The system of claim 10 , wherein the comparing the signature to the signatures comprises applying a fuzzy matching algorithm.

13. The system of claim 9 , wherein the categorizing comprises:

assigning the client mobile device having the unknown mobile device type into one of a plurality of categories, each category associated with one or more features and each feature having a feature level selected from a plurality of feature levels.

14. The system of claim 9 , wherein each of the benchmark applications has a specified time for completion.

15. The system of claim 14 , wherein one of the benchmark applications is selected from a group comprising determining how many primes are calculated within a first predetermined period of time and determining how many images are compared from an image set within a second predetermined period of time.

16. The system of claim 9 , wherein the system further comprises:

identifying that the client mobile device of the unknown mobile device type has one or more missing performance metrics;

requesting that the client mobile device of the unknown mobile device type perform the benchmark applications corresponding the one or more missing performance metrics; and

receiving the one or more missing performance metrics.

17. A non-transitory processor-readable storage medium storing processor-executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising:

distributing benchmark applications to a plurality of client mobile devices, the benchmark applications configured to at least one of produce or collect one or more dynamic and static parameters as performance metrics for each client mobile device;

receiving the performance metrics from the plurality of client mobile devices;

comparing the performance metrics for a client mobile device having an unknown mobile device type to the performance metrics of client mobile devices having known mobile device types;

categorizing the client mobile device having the unknown mobile device type with one or more client mobile devices having known mobile device types according to similarity of the performance metrics for the client mobile device having the unknown mobile device type to the performance metrics of the one or more of the client mobile devices having known mobile device types, wherein at least one of a central processing unit or graphics processing unit of the client mobile device of the unknown mobile device type is different than for the one or more of the client mobile devices having the known mobile device types;

identifying feature levels for at least one feature of a social media application on the categorized client mobile device having the unknown mobile device type; and

distributing the identified feature levels for the at least one feature of the social media application to the categorized client mobile device having the unknown mobile device type for use by the categorized client mobile device to configure at least one feature of the social media application on the categorized client mobile device having the unknown mobile device type in accordance with the identified feature levels for the at least one feature of the social media application on the categorized client mobile device having the unknown mobile device type for more efficient processing of the social media application at the identified feature levels on the categorized client mobile device having the unknown mobile device type.

18. The non-transitory processor-readable storage medium of claim 17 , wherein the instructions causing the machine to compare the performance metrics comprises:

generating a signature from the performance metrics for the client mobile device having the unknown mobile device type; and

comparing the signature to signatures of client mobile devices having known mobile device types;

wherein the categorizing categorizes the client mobile device having the unknown mobile device type responsive to comparing the signatures.